Vision Detection Method for Picking Robots Based on Improved Faster R-CNN

doi:10.6041/j.issn.1000-1298.2024.01.004

IR > 机电工程学院

	Vision Detection Method for Picking Robots Based on Improved Faster R-CNN
其他题名	基于改进 Faster R — CNN 的苹果采摘视觉定位与检测方法
	Li, Cuiming; Yang, Ke; Shen, Tao; Shang, Zhengyu
	2024
发表期刊	Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery
ISSN	1000-1298
卷号	55 期号:1 页码:47-54
摘要	To address the issue of poor detection and positioning capabilities of fruit picking robots in scenes with densely distributed targets and fruits occluding each other, a method to improve the fruit detection and positioning of Faster R — CNN was proposed by introducing an efficient channel attention mechanism (ECA) and a multiscale feature fusion pyramid (FPN). Firstly, the commonly used VGG16 network was replaced with a ResNet50 residual network with strong expression capability and eliminate network degradation problem, thus extracting more abstract and rich semantic information to enhance the model’s detection ability for multiscale and small targets. Secondly, the ECA module was introduced to enable the feature extraction network to focus on local and efficient information in the feature map, reduce the interference of invalid targets, and improve the model’s detection accuracy. Finally, a branch and leaf grafting data augmentation method was used to improve the apple dataset and solve the problem of insufficient image data. Based on the constructed dataset, genetic algorithms were used to optimize K-means + + clustering and generate adaptive anchor boxes. Experimental results showed that the improved model had average precision of 96.16% for graspable apples and 86.95% for non-graspable apples, and the mean average precision was 92.79%, which was 15.68 percentages higher than that of the traditional Faster R — CNN. The positioning accuracy for graspable and non-directly graspable apples were 97.14% and 88.93 %, respectively, which were 12.53 percentages and 40.49 percentages higher than that of traditional Faster R — CNN. The weight was reduced by 38.20%. The computation time was reduced by 40.7 %. The improved model was more suitable for application in fruit-picking robot visual systems. © 2024 Chinese Society of Agricultural Machinery. All rights reserved.
关键词	Agricultural robots Feature extraction Genetic algorithms Image enhancement K-means clustering Semantics Apple picking robot Attention mechanisms Detection methods Distributed target Efficient channels Fast R — CNN Feature pyramid Picking robot Target localization Targets detection
DOI	10.6041/j.issn.1000-1298.2024.01.004
收录类别	EI
语种	中文
出版者	Chinese Society of Agricultural Machinery
EI入藏号	20240915630263
EI主题词	Fruits
EI分类号	731.5 Robotics ; 821.1 Agricultural Machinery and Equipment ; 821.4 Agricultural Products ; 903.1 Information Sources and Analysis
原始文献类型	Journal article (JA)
引用统计	无
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/169966
专题	机电工程学院
作者单位	School of Mechanical and Electrical Engineering, Lanzhou University of Technology, Lanzhou; 730050, China
第一作者单位	兰州理工大学
第一作者的第一单位	兰州理工大学
推荐引用方式 GB/T 7714	Li, Cuiming,Yang, Ke,Shen, Tao,et al. Vision Detection Method for Picking Robots Based on Improved Faster R-CNN[J]. Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery,2024,55(1):47-54.
APA	Li, Cuiming,Yang, Ke,Shen, Tao,&Shang, Zhengyu.(2024).Vision Detection Method for Picking Robots Based on Improved Faster R-CNN.Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery,55(1),47-54.
MLA	Li, Cuiming,et al."Vision Detection Method for Picking Robots Based on Improved Faster R-CNN".Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery 55.1(2024):47-54.